真实场景中通过可控图像编辑实施车辆检测器的伪装攻击
In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
AI总结：
本文提出了一种将车辆伪装攻击视为条件图像编辑问题的新框架，通过图像级和场景级生成策略提升攻击效果，实验表明其在COCO和LINZ数据集上显著降低检测器性能，同时保持车辆结构和提升人类感知的隐蔽性。
摘要：
深度神经网络（DNN）在计算机视觉中取得了显著成就，但仍然容易受到对抗性攻击的威胁。其中，伪装攻击通过操纵物体的可见外观来欺骗检测器，同时保持对人类的隐蔽性。本文提出了一种新的框架，将车辆伪装攻击视为一个条件图像编辑问题。具体而言，我们探索了图像级和场景级的伪装生成策略，并微调了ControlNet，直接在真实图像上合成伪装车辆。我们设计了一个统一的目标，共同 enforcing 车辆结构的忠实性、风格的一致性和对抗的有效性。在COCO和LINZ数据集上的广泛实验表明，我们的方法实现了更强的攻击效果，导致AP50下降超过38%，同时在保持车辆结构和提高人类感知的隐蔽性方面优于现有方法。此外，我们的框架能够有效泛化到未见过的黑盒检测器，并在物理世界中表现出有前途的可转移性。项目页面可在https://humansensinglab.github.io/CtrlCamo上找到
英文摘要：
Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an object's visible appearance to deceive detectors while remaining stealthy to humans. In this paper, we propose a new framework that formulates vehicle camouflage attacks as a conditional image-editing problem. Specifically, we explore both image-level and scene-level camouflage generation strategies, and fine-tune a ControlNet to synthesize camouflaged vehicles directly on real images. We design a unified objective that jointly enforces vehicle structural fidelity, style consistency, and adversarial effectiveness. Extensive experiments on the COCO and LINZ datasets show that our method achieves significantly stronger attack effectiveness, leading to more than 38% AP50 decrease, while better preserving vehicle structure and improving human-perceived stealthiness compared to existing approaches. Furthermore, our framework generalizes effectively to unseen black-box detectors and exhibits promising transferability to the physical world. Project page is available at https://humansensinglab.github.io/CtrlCamo
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
